Method and system for optimizing heat dissipation performance of multi-layer structure wire duct

Abstract

The invention provides a heat dissipation performance optimization method and system for a multi-layer structure wire duct, and relates to the technical field of performance optimization, and the method comprises the steps: executing the cable heating fitting analysis of a cable, and dividing the multi-layer structure wire duct into a plurality of heat management sub-regions; configuring a sensor array for each thermal management sub-area; performing work fitting on the multi-layer structure trunking cable, and establishing a calibration decision maker; after the calibration decision-making devices are distributed to a plurality of heat management subareas, incremental optimization is executed; performing a sliding window heat dissipation decision on the basis of the corresponding hot area distribution by using the calibration decision-making device after increment optimization; and multi-layer structure wire duct cable heat dissipation management is carried out. According to the invention, the technical problem that the heat dissipation efficiency is low due to the fact that the heat distribution between the cables is different, the heat management requirement of each area is difficult to process accurately, and some areas are overheated or uneven in temperature is solved, accurate heat dissipation management of each cable in the multi-layer structure wire duct is realized, and the heat dissipation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of performance optimization, and in particular to a method and system for optimizing the heat dissipation performance of a multi-layer structured cable duct. Background Art

[0002] A multi-layer cable trunking system is a device used for routing and managing electrical wires. It typically consists of multiple layers, each with its own specific function and structure, typically consisting of a base plate, side panels, and dividers. The base plate supports the entire trunking system, the side panels provide protection and isolation, and the dividers separate different types of wires or cables to prevent interference and damage. Traditional cable heat dissipation management often relies on static designs and is unable to dynamically adapt to changes in cable load, ambient temperature fluctuations, or other operating conditions. Cables in multi-layer cable trunking generate and distribute heat differently due to varying loads, power consumption, and operating conditions. Conventional heat dissipation solutions cannot accurately address the thermal management needs of each area, leading to overheating or uneven temperatures in certain areas, which directly impacts the cable's heat generation and cooling requirements. This failure to precisely match the heat distribution between different cable areas can easily lead to overheating or hypothermia, resulting in inefficient overall heat dissipation.

[0003] In summary, the existing technology has technical problems such as low heat dissipation efficiency due to different heat distribution between cables, which makes it difficult to flexibly respond to load changes and environmental fluctuations, resulting in overheating or uneven temperature in certain areas. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for optimizing the heat dissipation performance of a multi-layer structure cable duct, so as to solve the technical problems in the prior art that due to the different heat distribution between cables, it is difficult to flexibly respond to load changes and environmental fluctuations, resulting in overheating or uneven temperature in certain areas, resulting in low heat dissipation efficiency.

[0005] In view of the above problems, the present application provides a method and system for optimizing the heat dissipation performance of a multi-layer structure cable duct.

[0006] In the first aspect, the present application provides a method for optimizing the heat dissipation performance of a multi-layer structure cable trough, which is implemented by a heat dissipation performance optimization system for a multi-layer structure cable trough, wherein the method for optimizing the heat dissipation performance of the multi-layer structure cable trough includes: performing cable heating fitting analysis of the cable, and dividing the multi-layer structure cable trough into multiple thermal management sub-areas using the cable heating fitting analysis results; configuring a sensor array for each thermal management sub-area, and establishing a thermal zone distribution using the sensor array; performing work fitting on the cable of the multi-layer structure cable trough, establishing a heating zone fitting result, and establishing a calibration decision maker using the heating zone fitting result; after distributing the calibration decision maker to multiple thermal management sub-areas respectively, performing incremental optimization of the calibration decision maker; using the calibration decision maker after incremental optimization to perform sliding window heat dissipation decisions based on the corresponding thermal zone distributions; and using the sliding window heat dissipation decisions to perform heat dissipation management of the cable in the multi-layer structure cable trough.

[0007] Optionally, a collaborative decision trigger analysis is performed based on the sliding window heat dissipation decision; if the collaborative decision trigger analysis result is a trigger result, the hot zone distribution is sent to the collaborative sensor, and a collaborative request is reported, and a collaborative control decision is generated based on the collaborative request and the hot zone distribution, and the collaborative control decision is used to perform heat dissipation management of multi-layer structure cable troughs.

[0008] Optionally, if the temperature rise trend of any thermal management sub-zone meets the preset conditions in the sliding window, the thermal accumulation delay judgment of the adjacent sub-zone of the corresponding thermal management sub-zone is executed; if the thermal accumulation delay judgment of the adjacent sub-zone is passed, the collaborative decision trigger analysis result is the trigger result, and a temperature trend linkage instruction is established; after the thermal zone distribution is selected using the temperature trend linkage instruction, it is synchronized to the collaborative sensor; the collaborative sensor is used to make a thermal trend linkage decision for the associated sub-zone to generate a collaborative control decision.

[0009] Optionally, instantaneous start-up identification of cable loads is performed on the thermal management sub-area, and heat cluster aggregation judgment is performed according to the number of instantaneous starts; if the heat cluster aggregation judgment is passed, the collaborative decision trigger analysis result is the trigger result; after the heat cluster aggregation distribution is established, the collaborative sensor is used to perform multi-objective collaborative optimization to establish a collaborative control decision, and the multi-objective collaborative optimization includes spatial heat redistribution optimization, duct load linkage adjustment optimization, thermal capacity enhancement of adjacent thermal management sub-areas, and scheduling coordination optimization.

[0010] Optionally, control positioning is performed on all thermal management sub-areas with maximum heat dissipation power activated; the temperature control effect is verified using the control positioning result. If the temperature control effect verification result is a non-cooling result, the collaborative decision trigger analysis result is the trigger result; the shared heat dissipation requirements of adjacent sub-areas are established, and the shared heat dissipation requirements are used to generate collaborative control decisions.

[0011] Optionally, determine whether there is a shared air duct situation between the cooling thermal management sub-zone and the high-temperature thermal management sub-zone; if so, the collaborative decision trigger analysis result is the trigger result, and the cooling path transfer requirement of the high-temperature thermal management sub-zone is established, and the cooling path transfer requirement is used to generate a collaborative control decision.

[0012] Optionally, the abnormality recognition layer is activated to receive the real-time monitoring data of the sensor array and perform global abnormality analysis; and the thermal runaway trend trigger result of the global abnormality analysis is used to report the heat dissipation abnormality.

[0013] Optionally, the thermal runaway trend is used to establish high-temperature fault location; based on the high-temperature fault location, an emergency heat dissipation mechanism is activated to perform emergency management.

[0014] Optionally, a heat dissipation evaluation is established for each thermal management sub-area; adaptive reinforcement learning is performed on the calibration decision maker after incremental optimization using the heat dissipation evaluation, and heat dissipation management of the corresponding thermal management sub-area is performed using the calibration decision maker after adaptive reinforcement learning.

[0015] In the second aspect, the present application also provides a heat dissipation performance optimization system for a multi-layer structure cable trough, which is used to execute the heat dissipation performance optimization method for a multi-layer structure cable trough as described in the first aspect, wherein the heat dissipation performance optimization system for a multi-layer structure cable trough includes: a sub-area division module, which is used to perform cable heating fitting analysis of the cable, and divide the multi-layer structure cable trough into multiple thermal management sub-areas using the cable heating fitting analysis results; a sensor configuration module, which is used to configure a sensor array for each thermal management sub-area, and use the sensor array to establish a thermal zone distribution; a thermal partition fitting module, which is used to perform working fitting on the cable of the multi-layer structure cable trough, establish a thermal partition fitting result, and use the thermal partition fitting result to establish a calibration decision maker; a decision maker optimization module, which is used to distribute the calibration decision maker to multiple thermal management sub-areas respectively, and then perform incremental optimization of the calibration decision maker; a decision determination module, which is used to use the calibration decision maker after incremental optimization to perform sliding window heat dissipation decisions based on the corresponding thermal zone distribution; and a decision execution module, which is used to use sliding window heat dissipation decisions to perform heat dissipation management of cables in multi-layer structure cable troughs.

[0016] One or more technical solutions provided in this application have at least the following beneficial effects: By performing cable heating fitting analysis on the cable, the cable heating fitting analysis results are used to divide the multi-layer structure cable duct into multiple thermal management sub-areas; a sensor array is configured for each thermal management sub-area, and the sensor array is used to establish a thermal zone distribution; a working fitting is performed on the cable of the multi-layer structure cable duct to establish a heating zone fitting result, and a calibration decision maker is established using the heating zone fitting result; after the calibration decision maker is distributed to multiple thermal management sub-areas, incremental optimization of the calibration decision maker is performed; the calibration decision maker after incremental optimization is used to perform sliding window heat dissipation decisions based on the corresponding thermal zone distribution; and the sliding window heat dissipation decision is used to perform heat dissipation management of the cable in the multi-layer structure cable duct. In other words, the multi-layer structure cable duct is divided into multiple thermal management sub-areas by the heating fitting analysis results, and intelligent sensors are configured to monitor the cable temperature in real time, a calibration decision maker is established, and the output of the decision maker is continuously adjusted through incremental optimization, and a sliding window heat dissipation decision is performed, thereby achieving precise heat dissipation management of each cable in the multi-layer structure cable duct and improving heat dissipation efficiency.

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without any creative work.

[0019] Figure 1 This is a flow chart of the method for optimizing the heat dissipation performance of a multi-layer structure cable duct in this application.

[0020] Figure 2 This is a structural diagram of the heat dissipation performance optimization system of the multi-layer structure cable duct of this application.

[0021] Explanation of the reference numerals: sub-area division module 11 , sensor configuration module 12 , heating zone fitting module 13 , decision maker optimization module 14 , decision determination module 15 , decision execution module 16 . DETAILED DESCRIPTION

[0022] This application solves the technical problem in the prior art of low heat dissipation efficiency by providing a method and system for optimizing the heat dissipation performance of multi-layer cable ducts, which is that due to the different heat distribution between cables, it is difficult to flexibly respond to load changes and environmental fluctuations, resulting in overheating or uneven temperature in certain areas. The multi-layer cable duct is divided into multiple thermal management sub-areas based on the results of heat fitting analysis, and intelligent sensors are configured to monitor cable temperatures in real time. A calibration decision maker is established, and the output of the decision maker is continuously adjusted through incremental optimization. A sliding window heat dissipation decision is executed, achieving precise heat dissipation management of each cable in the multi-layer cable duct and improving heat dissipation efficiency.

[0023] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0024] For example, see the attached Figure 1 The present application provides a method for optimizing the heat dissipation performance of a multi-layer structured wire trough, wherein the method is executed by a heat dissipation performance optimization system for a multi-layer structured wire trough, and the method specifically includes the following steps: S100: performing cable heating fitting analysis on the cable, and dividing the multi-layer structure cable duct into a plurality of thermal management sub-areas using the cable heating fitting analysis result.

[0025] Specifically, when power is applied to a cable, the current flowing through the resistance generates heat, which is known as cable heating. This heat generation is affected by factors such as current flow, operating time, and cable resistance. Cable heating is analyzed by fitting the cable's heat generation, taking into account cable specifications (such as resistance), load (current flow), and operating environment (temperature, humidity, etc.). Fitting analysis is a mathematical method used to infer or predict unobserved data using known data. This allows for accurate simulation and prediction of cable heating based on the cable's operating conditions, load, and environmental factors. Heat generation is typically estimated by calculating the cable's current load and resistance: the product of the square of the cable resistance and the current load.

[0026] Collect basic cable data, such as cable material, outer diameter, length, type, and resistance. Also, collect load data during operation, such as the current flowing through the cable and its pattern of change (constant, pulsed, etc.). Also, record the temperature changes of the cable under different loads. Based on the collected experimental data, use regression analysis to establish a relationship model between cable heating and factors such as current load, resistance, and time. Once the relationship model is established, it needs to be verified. Actual cable heating data under different loads is measured, and the model's predictions are compared with the actual data. If the difference between the two is small, the model fits well and accurately predicts heating in different areas of the cable.

[0027] By fitting the analysis results, we can obtain heat generation data for different cable areas. Heat distribution varies across different areas, and based on these differences in heat generation, the cable routing area is divided into multiple thermal management sub-areas. The division criteria for each thermal management sub-area are typically based on heat load differences, ensuring a balance between the heat dissipation requirements and capacity of each area. In other words, based on the differences in heat generation across cable areas, if a particular area generates significantly more heat than others, that area will be individually separated for more specialized heat dissipation management.

[0028] Multi-layer cable trunking is divided into multiple thermal management sub-zones. The cables within each sub-zone generate approximately the same or similar amounts of heat, allowing for similar heat dissipation measures. For example, based on the heat distribution in different areas, they can be divided into high-heat sub-zones, medium-heat sub-zones, and low-heat sub-zones. By dividing the thermal management sub-zones, different heat dissipation strategies can be implemented based on the heat generation in each area, achieving personalized and differentiated heat dissipation management.

[0029] S200: configuring a sensor array for each thermal management sub-area, and establishing a thermal zone distribution using the sensor array.

[0030] Specifically, a sensor array is deployed in each thermal management subzone to monitor temperature changes within each subzone, enabling real-time tracking and management of cable heating. The sensor array may include intelligent sensors such as temperature sensors, humidity sensors, thermocouples, and infrared sensors, with different sensors selected based on the physical quantity to be monitored. The density and location of sensors should be determined based on the heat load distribution and the results of the cable heating fitting analysis. Generally, areas with higher heating require more sensors to provide more accurate data. For example, more temperature sensors should be deployed in areas with dense cables and higher heating; whereas, fewer sensors should be deployed in areas with lower heating or better ventilation.

[0031] The sensor array collects real-time temperature data from each sub-zone and transmits it to the control center. During data collection, the sensors should read data regularly, ensuring that the intervals between data collection are short enough to reflect the cable's heating status in real time. For areas with high loads or high heat generation, the data collection frequency can be increased. Based on the data collected from the sensor array, a heat map is created for each thermal management sub-zone, reflecting the temperature gradients at different locations within each sub-zone. This heat map can identify areas with excessively high temperatures or large temperature differences, allowing for timely detection of potential thermal management issues.

[0032] The heat zone distribution maps obtained by the sensor arrays of multiple thermal management sub-zones are integrated to obtain the overall heat zone distribution, including the temperature distribution of different areas. Based on the heat zone distribution and actual temperature changes, the heat dissipation strategy is automatically adjusted, such as adjusting the fan speed and starting the cooling device. For example, Area 1 is a high-heat area with a high load and high heat generation, requiring a large and dense deployment of sensors, such as 20 sensors; while Area 2 is a low-heat area with a low load and good ventilation, requiring a smaller number of sensors, such as 5. By configuring a sensor array in each thermal management sub-zone and using these sensors to establish a heat zone distribution, the temperature of each sub-zone can be accurately monitored and managed, which helps to promptly detect and resolve overheating or uneven temperature problems and improve heat dissipation efficiency.

[0033] S300: Performing working fitting on the multi-layer structure cable duct, establishing a heating zone fitting result, and establishing a calibration decision maker using the heating zone fitting result.

[0034] Specifically, multi-layer cable trunking refers to a cable system arranged in multiple layers of trunking, typically used in applications such as large-scale power transmission and data communications. In cable management, multi-layer cable trunking typically involves multiple cables laid in parallel and stacked together. Due to the limited space between multiple cables, heat can accumulate between them, necessitating effective temperature control and heat dissipation management.

[0035] Performing a working fit on multi-layer cable trunking cables involves establishing a model that simulates the cable's heating conditions based on factors such as the load and temperature in the cable's actual operating environment. Load data and ambient temperature data are collected for the cable under operating conditions, and a thermal model of the cable under operating conditions is established through test data fitting. Specifically, data is collected for the cable under different operating conditions, including current, load, cable material, and external ambient temperature. Based on the collected data, mathematical fitting methods are used to derive a formula that reflects the cable's heating trend and can simulate the cable's temperature distribution under different operating conditions. Working fit involves using numerical methods to fit the actual heating data of the cable under different operating conditions (such as load, current, and ambient temperature), thereby deriving a cable heating model that reflects the cable's temperature distribution under different operating conditions.

[0036] Based on data from the cable under different operating conditions, the relationship between cable temperature and parameters such as current and load is analyzed, and a relationship formula is constructed. This involves collecting temperature data under different current, load, and environmental conditions. For each set of data, the least squares method is used to calculate fitting parameters. The resulting fitting equation is applied to other untested operating conditions to predict the cable temperature distribution under these conditions. This process is repeated repeatedly to find the best-fitting curve or equation by minimizing the squared error between the predicted and measured cable temperature values.

[0037] Through fitting analysis, the heat generation zoning for each thermal management sub-zone is determined, known as the heat generation zoning fitting result. This heat generation zoning fitting result represents the heat generation conditions of each thermal management sub-zone, based on the temperature distribution and heat generation characteristics of the cable under operating conditions. The main function of the calibration decision maker is to adjust the cable's heat dissipation strategy in real time based on the current operating conditions (such as current, load, and ambient temperature) to ensure that the temperature of each thermal management sub-zone remains within a reasonable range. Its goal is to automatically optimize the heat dissipation measures for each sub-zone through accurate temperature prediction to avoid local overheating. Based on the heat generation zoning fitting results, the decision maker's operating parameters are calibrated to generate cooling decisions tailored to the actual heat zone distribution.

[0038] Through working fitting and heat zone fitting, the temperature changes in each area can be accurately predicted. The calibration decision maker automatically adjusts the heat dissipation plan according to the distribution of hot zones to ensure that the cable can maintain a reasonable temperature under different working conditions and avoid overheating.

[0039] S400: After distributing the calibration decision maker to a plurality of thermal management sub-areas, incremental optimization of the calibration decision maker is performed.

[0040] Specifically, the calibration decision makers are decentralized to multiple thermal management sub-areas for incremental optimization, enabling each sub-area to possess independent thermal management judgment and response capabilities. Each sub-area has a calibration decision maker to manage heat dissipation within that area. Each thermal management sub-area continuously monitors operating status and environmental conditions using a configured sensor array (including temperature, current, and humidity sensors). The calibration decision maker predicts the temperature of that sub-area based on real-time data. The performance of each calibration decision maker is monitored, including the deviation between its predicted heat generation and the actual measured data. Specifically, the temperature of each sub-area is predicted based on current, load, and ambient temperature. The actual temperature measured by the sensors is compared with the predicted temperature to determine the temperature error. Based on real-time error feedback, the decision model parameters are adjusted to better adapt to actual operating conditions and gradually improve heat dissipation.

[0041] Use the temperature error fed back in real time to adjust the original model parameters, such as the least squares method. Analyze the collected data to identify the reasons for the inaccurate predictions of the decision maker, and adjust the parameters of the decision maker based on the errors. For example, if it is found that the decision maker underestimates the heat generation of certain areas, adjust the model parameters to increase the predicted temperature of these areas. Apply the adjusted parameters to the calibration decision maker and test to verify whether its performance has improved. This process is iterative and requires multiple adjustments and tests to achieve optimal performance. With the optimized model, the calibration decision maker will re-evaluate the heat dissipation requirements of the sub-area. If the optimized temperature prediction still exceeds the set safety range (such as 70°C), the decision maker will activate additional cooling measures, such as adjusting the fan speed or enabling the liquid cooling system.

[0042] For multiple thermal management sub-zones within a multi-layer cable trunking structure, the calibration decision maker performs the aforementioned incremental optimization process for each sub-zone. Each sub-zone undergoes independent error feedback and parameter optimization, ensuring that the cooling system in each zone dynamically adjusts to local temperature fluctuations. Through real-time incremental optimization, the calibration decision maker accurately predicts temperature changes in each sub-zone, mitigating overheating and inefficient cooling.

[0043] S500: Using the incrementally optimized calibration decision maker, a sliding window heat dissipation decision is made based on the corresponding hot zone distribution.

[0044] Specifically, the incrementally optimized calibration decision maker, combined with the corresponding heat zone distribution for each sub-region, uses a sliding window to analyze recent temperature data. A sliding window is a time period whose size determines the temperature data considered for decision making. For example, if the sliding window is set to 10 minutes, the decision maker will make cooling decisions based on the temperature change data from the past 10 minutes. The choice of window size affects the response speed and stability of the decision and is typically determined based on actual application requirements. Within each sliding window, the calibration decision maker analyzes temperature changes during that period and determines the cooling requirements for that sub-region based on the analysis results. For example, if the temperature in a certain area has continued to rise over the past 10 minutes, the decision maker will adjust the intensity of cooling equipment (such as fans, air conditioners, or liquid cooling systems) to accelerate heat dissipation. If the temperature is low, the power consumption of the cooling equipment will be reduced to save energy.

[0045] The calibration decision maker adjusts the cooling measures for each sub-zone based on feedback from the sliding window. After each decision is made, the sliding window slides forward to the next time period. New temperature data is continuously added, and the decision maker continues to make cooling decisions based on this new data. This dynamic process enables rapid and effective response to real-time temperature changes. After each cooling decision within the sliding window, the decision maker continues to refine its model by comparing temperature data with predicted results (via error feedback). As data accumulates, incremental optimization continuously improves the decision maker's ability to predict temperature changes, further enhancing the accuracy of sliding window decisions. Furthermore, the distribution of hot zones may change over time. The calibration decision maker needs to continuously update its decisions to adapt to these changes. This means that the sliding window needs to continuously move to include the latest data.

[0046] Through sliding window decision-making, the calibration decision maker can respond to the dynamic needs of temperature changes in each sub-zone in real time and accurately, ensuring that cooling decisions can be adjusted in a timely manner to avoid overheating or excessive cooling, and effectively manage the cooling conditions of each thermal management sub-zone.

[0047] S600: Utilizes sliding window cooling decision-making to manage heat dissipation in multi-layer cable ducts.

[0048] Furthermore, the present application S600 includes: A collaborative decision trigger analysis is performed based on the sliding window heat dissipation decision; if the collaborative decision trigger analysis result is a trigger result, the hot zone distribution is sent to the collaborative sensor, and a collaborative request is reported, and a collaborative control decision is generated according to the collaborative request and the hot zone distribution, and the collaborative control decision is used to perform heat dissipation management of multi-layer structure cable troughs.

[0049] Specifically, the sliding window cooling decision is a cooling strategy that is adjusted by analyzing temperature changes over a certain period of time. This is the initial cooling adjustment strategy. For example, if the temperature of a sub-area has risen too quickly over a period of time, or if the temperature has approached the upper limit of safety, the calibration decision maker will make a cooling decision based on this data.

[0050] Based on the sliding window decision results, the temperature rise trends of different thermal management sub-areas are analyzed. If a particular area shows a significant temperature rise trend, or if multiple sub-areas show signs of heat clustering (i.e., temperatures in multiple areas are too high and may affect each other), a decision is made to determine whether the collaborative decision triggering conditions should be met. Specifically, if the analysis results meet the preset triggering conditions, such as if the temperature rise trend exceeds a set threshold or if hotspot clustering reaches a certain level, the collaborative sensor is triggered.

[0051] Collaborative decision-making trigger analysis determines whether coordination of cooling requirements across different sub-zones is necessary. If the temperature rise trend or heat clusters (heat-intensive areas) in certain areas reach the set trigger conditions, collaborative decision-making is triggered. The collaborative sensor receives information from multiple thermal management sub-zones and analyzes any interrelated thermal trends or conflicts in cooling requirements. Its goal is to integrate cooling information from multiple sub-zones and coordinate cooling decisions across them.

[0052] If the collaborative decision-making trigger analysis indicates that collaborative decision-making is necessary, a trigger signal is sent to the collaborative sensor. Simultaneously, a collaborative request is issued, indicating that a sub-zone needs to collaborate with other sub-zones to resolve heat dissipation issues. The collaborative sensor receives hot zone distribution data and analyzes temperature trends and potential heat dissipation conflicts between zones. It also determines the temperature linkage between adjacent sub-zones, identifying zones with potentially conflicting or interlocking heat dissipation requirements.

[0053] After receiving the hot zone distribution and collaboration requests, the collaborative sensor analyzes the cooling status of multiple sub-zones, analyzes any interlocking thermal trends or conflicts in cooling requirements, and generates appropriate collaborative control decisions. For example, it may be necessary to increase cooling measures in certain areas or adjust cooling equipment in adjacent areas to prevent excessive temperature increases or ineffective heat dissipation.

[0054] The resulting collaborative control decisions are used to manage the heat dissipation of cables in multi-layer cable trays, adjusting the cooling systems of each sub-zone to optimize the overall cooling effect and ensure that the temperature of all sub-zones remains within a safe range. For example, increasing fan speed, adjusting the liquid cooling system, and initiating additional cooling measures can prevent overheating or localized temperature unevenness.

[0055] After executing collaborative control decisions, the temperature of each sub-zone continues to be monitored and optimized based on real-time data. If any decisions are found to be inconsistent with expectations, further trigger analysis and collaborative control decision adjustments are performed, forming a closed-loop feedback mechanism to ensure the stability and efficiency of the cooling system in long-term operation. Collaborative decision-making trigger analysis based on sliding window cooling decisions coordinates temperature linkages and cooling conflicts across different thermal management sub-zones. Through collaborative sensor analysis and control decisions, dynamic and precise cooling management is achieved, optimizing energy use, avoiding overheating, and improving overall cooling efficiency and operational stability.

[0056] Furthermore, the present application further comprises the following steps: If the temperature rise trend of any thermal management sub-zone meets the preset conditions in the sliding window, the thermal accumulation delay judgment of the adjacent sub-zone of the corresponding thermal management sub-zone is executed; if the thermal accumulation delay judgment of the adjacent sub-zone is passed, the collaborative decision trigger analysis result is used as the trigger result, and a temperature trend linkage instruction is established; after the thermal zone distribution is selected using the temperature trend linkage instruction, it is synchronized to the collaborative sensor; the collaborative sensor is used to make a thermal trend linkage decision for the associated sub-zone to generate a collaborative control decision.

[0057] Specifically, a sensor array monitors the temperatures of multiple thermal management subzones executing sliding window cooling decisions in real time. Sliding window analysis is then used to monitor the temperature rise trends of the cables in real time. This involves sliding a fixed-size window across the time series data to analyze data trends. If the temperature rise trend of any of the multiple thermal management subzones meets a preset condition within the sliding window (e.g., the rate of temperature rise exceeds a set threshold), a thermal accumulation delay determination is performed on the corresponding thermal management subzone's adjacent subzones. In other words, if the temperature trend of a subzone meets the triggering condition, a thermal accumulation delay determination is performed on the adjacent subzones to determine whether the temperature rise of the current subzone will affect them, particularly those located between hot zones. If the temperature trends of the adjacent subzones are within a controllable range and the impact of heat accumulation is within the delay range and does not cause overheating, no adjustment strategy is required, and the collaborative decision-making will not be penalized.

[0058] If the adjacent sub-zone heat accumulation delay judgment passes, it indicates that the temperature rise in the current sub-zone will cause heat accumulation in adjacent sub-zones, thereby affecting the cooling effect of adjacent sub-zones (such as insufficient cooling capacity or excessive temperature). This triggers collaborative decision analysis, requiring collaborative decision-making to optimize the cooling strategy. If the collaborative decision trigger analysis result is a trigger result, a temperature trend linkage instruction is generated to coordinate the cooling strategies of adjacent sub-zones to ensure the overall cooling effect is optimal.

[0059] According to the temperature trend linkage instruction, the corresponding hot zone distribution is selected and synchronized to the collaborative sensor. According to the corresponding hot zone distribution and temperature trend linkage instruction, the thermal trend linkage decision of the associated sub-zone is made, that is, the thermal trend of these related sub-zones is analyzed and the heat dissipation strategy is adjusted accordingly. The heat dissipation systems of multiple related sub-zones (such as fan speed, liquid cooling system, etc.) are adjusted to ensure that the temperature of all sub-zones is within a safe range and a collaborative control decision is obtained. The generated collaborative control decision is applied to each thermal management sub-zone in the multi-layer structure cable duct to ensure the reasonable allocation and dynamic adjustment of heat dissipation measures. Through the heat accumulation delay judgment of adjacent sub-zones and the execution of temperature trend linkage instructions, the heat dissipation measures of each sub-zone in the multi-layer structure cable duct can be dynamically coordinated to avoid overheating problems caused by heat accumulation in certain areas.

[0060] Furthermore, the present application further comprises the following steps: The instantaneous start-up identification of the cable load is performed on the thermal management sub-area, and the heat cluster aggregation judgment is performed according to the number of instantaneous starts; if the heat cluster aggregation judgment is passed, the collaborative decision trigger analysis result is the trigger result; after the heat cluster aggregation distribution is established, the collaborative sensor is used to perform multi-objective collaborative optimization and establish a collaborative control decision. The multi-objective collaborative optimization includes spatial heat redistribution optimization, duct load linkage adjustment optimization, thermal capacity enhancement of adjacent thermal management sub-areas, and scheduling coordination optimization.

[0061] Specifically, the thermal management sub-zones are used to identify instantaneous cable load startups. This involves real-time monitoring of dynamic changes in cable loads, particularly instantaneous increases and decreases in cable loads. For example, when multiple cable loads start or stop simultaneously, cable heating can change instantaneously. Using load sensors, temperature sensors, and current sensors, data acquisition equipment is used to acquire the load status of each sub-zone's cables in real time. Data analysis identifies instantaneous load changes. Sudden increases in load or simultaneous startups of multiple cables are identified, and the number of instantaneous startups is recorded.

[0062] When instantaneous start-up identification results indicate simultaneous increases in load on multiple cables, the heat distribution in that area needs to be evaluated. If the heat generated by these cables is concentrated in a small area, forming a heat cluster (i.e., heat concentration), this is considered a heat cluster. By monitoring the number of cable load starts in the area and combining it with the temperature distribution, we can assess whether this will lead to excessive temperatures. If so, a collaborative decision analysis is triggered.

[0063] By determining whether heat clustering will lead to overheating, a positive assessment confirming the presence of heat clusters in a specific area triggers collaborative decision-making analysis to prevent overheating in that area. When the collaborative decision-making analysis is triggered, a heat cluster distribution is established—a detailed description of the heat cluster, including its location, size, and intensity. This distribution identifies areas within multiple sub-areas where heat concentration is present, helping to determine which areas require adjustments to cooling strategies.

[0064] Based on the distribution of heat clusters, multi-objective collaborative optimization is performed, including spatial heat redistribution optimization, duct load linkage adjustment optimization, heat capacity enhancement of adjacent thermal management sub-areas, and scheduling coordination optimization. Spatial heat redistribution optimization is based on real-time changes in heat distribution within the entire thermal management area, transferring heat from higher temperature areas to lower temperature areas, thereby making the heat distribution more uniform and avoiding overheating in certain areas. An objective function is constructed based on spatial heat redistribution optimization, duct load linkage adjustment optimization, heat capacity enhancement of adjacent thermal management sub-areas, and scheduling coordination optimization. Constraints are constructed based on factors such as the physical limitations of the heat dissipation equipment, changes in ambient temperature, and the mutual influence of heat between sub-areas. A particle swarm optimization algorithm is used for optimization.

[0065] A particle swarm is randomly initialized, with each particle representing a solution containing multiple parameters (such as cooling resource allocation and air duct adjustment values). Each particle's initial position and velocity are randomly generated. The fitness of each particle is calculated based on the objective function. Based on the fitness values ​​of each objective function, the particle's velocity and position are adjusted using the particle swarm optimization update formula to search for the optimal solution. At each optimization step, the relationships between multiple objectives are balanced using the Pareto front, generating a series of optimal solutions. Ultimately, the most appropriate decision is selected based on the objective weights and actual needs.

[0066] Through multi-objective optimization, collaborative control decisions are made, taking into account multiple factors such as temperature distribution, load variations, and resource utilization. This ensures stable temperatures in each sub-zone and avoids wasted cooling resources. Based on the optimization results, the operation of equipment such as air ducts and coolers is adjusted to ensure effective temperature control in each sub-zone and optimal resource allocation. This not only adjusts the cooling of individual zones but also further optimizes the cooling effect of the entire system through the synergy of adjacent sub-zones. By identifying the instantaneous start-up of cable loads and the accumulation of heat clusters in real time, potential heat clusters can be identified and controlled at an early stage, preventing high-temperature areas from causing equipment damage or reduced efficiency.

[0067] Furthermore, the present application further comprises the following steps: Control positioning is performed on all thermal management sub-areas under the activation of maximum heat dissipation power; the temperature control effect is verified using the control positioning results. If the temperature control effect verification result is a non-cooling result, the collaborative decision trigger analysis result is the trigger result; the shared heat dissipation requirements of adjacent sub-areas are established, and the shared heat dissipation requirements are used to generate collaborative control decisions.

[0068] Specifically, the fan heat dissipation capacity of multiple thermal management sub-areas is monitored to determine whether the fans have reached their maximum output power. Based on the control positioning results, the temperature control effect of sub-areas where independent temperature control fails is verified. If the fan in a sub-area has been running at maximum power, but the temperature in that area still cannot be effectively reduced, it is determined that the independent temperature control of that area has failed, that is, the heat dissipation has failed, and it is necessary to request adjacent sub-areas to share the air duct flow. Control positioning is performed on all thermal management sub-areas to determine the heat dissipation capacity of each sub-area when the maximum heat dissipation power is activated. Through control positioning, areas that cannot meet temperature control requirements are identified.

[0069] In other words, in each thermal management sub-zone, the performance of heat dissipation equipment (such as fans, liquid cooling systems, etc.) is monitored in real time. When it is detected that the heat dissipation equipment in a sub-zone has reached maximum power, the temperature of that zone is evaluated. Assuming that the heat dissipation equipment in that zone, such as a small pump cooling system, has reached 500W (i.e., maximum power), but the temperature still cannot drop to the predetermined safe temperature range, control positioning is performed to check whether the independent temperature control of that zone has failed. If it is found that the temperature is still above the set threshold (e.g., the temperature exceeds 70°C) and the heat dissipation equipment is already operating at maximum power, the system will determine that the independent temperature control of that sub-zone has failed, that is, the sub-zone cannot achieve independent temperature control.

[0070] The criterion for triggering collaborative decision-making is that if a sub-area cannot cool down independently and the heat dissipation equipment in the area can no longer continue to improve the heat dissipation capacity, the collaborative mechanism will be activated to seek help from adjacent sub-areas to jointly undertake the heat dissipation task.

[0071] By calculating the heat dissipation capacity of adjacent sub-zones, it is determined whether these sub-zones have sufficient cooling resources to help the current sub-zone reduce its temperature. It is also determined whether the adjacent sub-zones have sufficient airflow, cooling capacity, and other resources to take over some of the cooling tasks. Assuming that the airflow of the adjacent sub-zone is sufficient and can share some of the cooling tasks without affecting its own temperature control, a collaborative control decision is generated, instructing the adjacent sub-zone to adjust its airflow to help dissipate heat in the current area. Based on the shared cooling needs, collaborative control decisions are generated, including adjusting fan speed and direction, reallocating cooling resources, and other measures to ensure that adjacent sub-zones can effectively reduce the temperature of sub-zones that cannot independently control their temperatures.

[0072] By applying collaborative control decisions to heat management within multi-layer cable trunking, airflow and other cooling parameters are adjusted to effectively share the heat dissipation burden in overheated areas, effectively balancing the temperature control requirements across different sub-zones within the multi-layer trunking structure and preventing the spread of overheating. Through this collaborative mechanism, each sub-zone can share the heat dissipation task based on actual needs, thereby improving the overall system's cooling performance.

[0073] Furthermore, the present application further comprises the following steps: Determine whether there is a shared air duct between the cooling thermal management sub-zone and the high-temperature thermal management sub-zone; if so, the collaborative decision trigger analysis result is the trigger result, and the cooling path transfer requirement of the high-temperature thermal management sub-zone is established, and the cooling path transfer requirement is used to generate a collaborative control decision.

[0074] Specifically, cooling thermal management subzones are areas within a thermal management system specifically designed to reduce temperatures. These subzones typically operate at lower temperatures and are primarily controlled by cooling equipment (such as fans and coolant systems). High-temperature thermal management subzones are areas within a thermal management system with higher temperatures. These areas are typically under higher loads, have greater heat dissipation requirements, and require strict temperature control to prevent equipment damage. Analyze the thermal management structure of the entire multi-layer cable trunking structure and determine whether each thermal management subzone (cooling and high-temperature) shares the same ventilation duct.

[0075] If the cooling and high-temperature thermal management sub-zones share the same air duct, the cooling path must accommodate the heat dissipation needs of both. If the heat dissipation demand of the high-temperature area is too high, this may affect the temperature control effectiveness of the cooling area, causing the temperature in the cooling area to rise and affecting cooling efficiency. If the cooling and high-temperature thermal management sub-zones share the same air duct, there is a conflict in air duct resources. This requires triggering collaborative decision-making and taking coordinated measures to manage heat dissipation to ensure that the cooling air duct can effectively serve the cooling thermal management sub-zone.

[0076] Establish cooling path transfer requirements for high-temperature thermal management sub-zones, redistribute cooling airflow or adjust coolant flow paths, and determine how much cooling duct resources need to be transferred from high-temperature areas to cooling areas to improve cooling efficiency. Decisions on cooling path transfers may include adjusting fan speeds, modifying duct allocations, and enabling other cooling devices to ensure that cooling ducts can effectively serve the cooling thermal management sub-zones without affecting the high-temperature thermal management sub-zones. By determining whether cooling and high-temperature thermal management sub-zones share air ducts, uneven resource allocation can be promptly identified, avoiding uneven heat dissipation caused by insufficient resources, ensuring that temperatures in each zone are effectively controlled, and improving overall heat dissipation efficiency.

[0077] Furthermore, the present application further comprises the following steps: Activate the abnormality recognition layer, receive the real-time monitoring data of the sensor array with the abnormality recognition layer, and perform global abnormality analysis; use the thermal runaway trend trigger result of the global abnormality analysis to report the heat dissipation abnormality.

[0078] Specifically, the anomaly identification layer is a key component responsible for real-time monitoring and analysis of data from various sensor arrays to identify anomalies, particularly those that could lead to system failures or safety hazards. Activating the anomaly identification layer initiates the relevant monitoring and analysis modules to ensure that the anomaly identification layer can receive data from the sensor array in real time. The anomaly identification layer receives real-time monitoring data from the sensor array, processes and analyzes it, and aggregates and processes data from all thermal management sub-zones to identify potential anomaly patterns. For example, if the temperature of multiple sub-zones exceeds a set threshold and this upward trend is not promptly adjusted, a global anomaly may occur. Global anomaly analysis combines the temperature changes of each sub-zone, the load status, and the performance of the cooling system to identify whether there is a global cooling problem or a local hotspot.

[0079] During global anomaly analysis, potential thermal runaway trends are identified. For example, if the temperature of a sub-zone continues to rise and approaches the set temperature threshold, and existing cooling measures cannot effectively reduce the temperature, this is determined to be a thermal runaway trend. Once a thermal runaway trend is identified, an alarm is triggered or an automatic anomaly report is automatically issued, indicating that the temperature control system may not function as expected, posing a risk. A thermal runaway trend refers to a sustained temperature increase in one or more areas of the system, with a tendency to further intensify.

[0080] Based on the analysis of thermal runaway trends, thermal anomalies are immediately generated and reported, including the cause, location, event, severity, and recommended actions. This provides timely warnings to operators or automatically initiates emergency measures to prevent potential equipment damage or safety incidents. By activating the anomaly identification layer and performing global anomaly analysis, the system monitors and manages the cooling status of the entire multi-layer cable trunking system in real time, enabling timely identification and response to potential cooling issues.

[0081] Furthermore, the present application further comprises the following steps: The thermal runaway trend is used to establish a high-temperature fault location; based on the high-temperature fault location, an emergency heat dissipation mechanism is activated to perform emergency management.

[0082] Specifically, high-temperature fault location is performed based on thermal runaway trends. By analyzing the temperature data of each sub-area and its changing trends, it is possible to identify which areas or devices have excessively high temperatures, and further analyze the source of the temperature change. High-temperature fault location is not limited to identifying the specific fault area, but also includes diagnosing the cause of the excessive temperature, such as decreased cooling system efficiency, excessive load, or other reasons. High-temperature fault location refers to accurately identifying and locating the specific location of excessive temperature or faults based on temperature data from each area of ​​the system. By analyzing temperature change trends, it is possible to determine which sub-areas or devices have abnormally high temperatures and locate them as potential sources of faults.

[0083] Based on the identified high-temperature fault, an emergency cooling mechanism is activated to prevent further temperature rise and irreversible damage to the equipment. For example, if the primary cooling system fails to function effectively, backup cooling equipment such as additional fans or a liquid cooling system is activated. For liquid cooling systems, the coolant flow rate or temperature is adjusted to improve heat exchange efficiency. After the emergency cooling mechanism is activated, temperature changes are continuously monitored and the cooling strategy is adjusted based on the feedback.

[0084] Emergency management is the process of rapidly responding and repairing equipment or system failures or anomalies through a series of measures. Based on the identified high-temperature fault and its location, an alarm is issued, and the anomaly is reported to maintenance personnel or system administrators through a notification mechanism. After the cooling mechanism is activated, the technical team conducts an on-site inspection to determine the root cause of the fault and perform repairs. The time, location, cause, and emergency response measures for all anomalies are also recorded. Through real-time monitoring and high-temperature fault location, an immediate response is achieved when equipment temperature anomalies occur, rapidly activating the emergency cooling mechanism, reducing the window of time during which the temperature rises and thereby minimizing the risk of equipment damage.

[0085] Furthermore, the present application further comprises the following steps: Establish a heat dissipation evaluation for each thermal management sub-area; use the heat dissipation evaluation to perform adaptive reinforcement learning on the calibration decision maker after incremental optimization, and use the calibration decision maker after adaptive reinforcement learning to perform heat dissipation management on the corresponding thermal management sub-area.

[0086] Specifically, heat dissipation evaluation indicators are established for each thermal management sub-zone to quantitatively or qualitatively analyze the heat dissipation performance of each sub-zone. These indicators typically use temperature, heat dissipation power, and wind speed to assess the heat dissipation capacity of each zone and determine whether there are problems such as uneven heat dissipation and overheating. Each thermal management sub-zone is evaluated based on real-time monitored data (such as temperature, humidity, wind speed, and load).

[0087] The calibration decision maker optimizes based on the heat dissipation evaluation results, gradually improving its decision-making strategy. For example, in the initial stages, the calibration decision maker relies on certain basic rules or experience. However, as data accumulates, the decision maker adjusts the heat dissipation strategy based on actual temperature fluctuations and heat dissipation requirements to make it more suitable for the actual environment. By interacting with the environment, the calibration decision maker adjusts the decision-making process based on real-time heat dissipation evaluations (such as temperature error and heat dissipation efficiency). For example, if the temperature in a certain area continuously exceeds a set threshold, the calibration decision maker will learn that this area requires higher heat dissipation capacity and thus optimize measures such as fan speed and increasing coolant flow.

[0088] As the heat dissipation evaluation is continuously updated, the calibration decision maker gradually optimizes its decision model based on actual feedback data. This optimization is incremental, with each optimization fine-tuning the results of the previous optimization to achieve higher accuracy. During this incremental optimization process, the calibration decision maker can adjust the heat dissipation strategy in real time. Based on the incrementally optimized decision maker, an adaptive learning method automatically adjusts the heat dissipation strategy based on real-time data. This is similar to traditional reinforcement learning, in which the intelligent agent (the calibration decision maker) learns the optimal strategy through continuous interaction with the environment (the actual situation in the thermal management sub-area).

[0089] Adaptive reinforcement learning continuously adjusts control strategies based on feedback, learning through exploration (trying different cooling measures) and exploitation (applying the currently optimal strategy). Within each thermal management subzone, the system gradually improves and adjusts the cooling control strategy based on feedback data. During the adaptive reinforcement learning process, the decision maker automatically adapts to varying cooling requirements and effectively dissipates heat by adjusting fan speeds, liquid cooling systems, and other methods. Through incremental optimization and adaptive reinforcement learning, the decision maker can precisely adjust cooling measures for each subzone, enabling each zone to dynamically adjust to its actual cooling needs to address varying environmental conditions and further improve the accuracy and robustness of cooling control.

[0090] In summary, the method for optimizing the heat dissipation performance of a multi-layer cable duct provided in this application has the following beneficial effects: By performing cable heating fitting analysis on the cable, the cable heating fitting analysis results are used to divide the multi-layer structure cable duct into multiple thermal management sub-areas; a sensor array is configured for each thermal management sub-area, and the sensor array is used to establish a thermal zone distribution; a working fitting is performed on the cable of the multi-layer structure cable duct to establish a heating zone fitting result, and a calibration decision maker is established using the heating zone fitting result; after the calibration decision maker is distributed to multiple thermal management sub-areas, incremental optimization of the calibration decision maker is performed; the calibration decision maker after incremental optimization is used to perform sliding window heat dissipation decisions based on the corresponding thermal zone distribution; and the sliding window heat dissipation decision is used to perform heat dissipation management of the cable in the multi-layer structure cable duct. In other words, the multi-layer structure cable duct is divided into multiple thermal management sub-areas by the heating fitting analysis results, and intelligent sensors are configured to monitor the cable temperature in real time, a calibration decision maker is established, and the output of the decision maker is continuously adjusted through incremental optimization, and a sliding window heat dissipation decision is performed, thereby achieving precise heat dissipation management of each cable in the multi-layer structure cable duct and improving heat dissipation efficiency.

[0091] In the second embodiment, based on the same inventive concept as the method for optimizing the heat dissipation performance of the multi-layer structure wire duct in the first embodiment, the present application also provides a heat dissipation performance optimization system for the multi-layer structure wire duct, please refer to the attached Figure 2 The heat dissipation performance optimization system of the multi-layer structure trunking includes: The sub-area division module 11 is used to perform cable heating fitting analysis of the cable, and divide the multi-layer structure cable duct into multiple thermal management sub-areas using the cable heating fitting analysis results; the sensor configuration module 12 is used to configure a sensor array for each thermal management sub-area, and use the sensor array to establish a thermal zone distribution; the heating zone fitting module 13 is used to perform working fitting on the multi-layer structure cable duct cable, establish a heating zone fitting result, and use the heating zone fitting result to establish a calibration decision maker; the decision maker optimization module 14 is used to distribute the calibration decision maker to multiple thermal management sub-areas respectively, and then perform incremental optimization of the calibration decision maker; the decision determination module 15 is used to use the calibration decision maker after incremental optimization to perform sliding window heat dissipation decisions based on the corresponding thermal zone distribution; the decision execution module 16 is used to use the sliding window heat dissipation decision to perform heat dissipation management of the multi-layer structure cable duct cable.

[0092] Furthermore, the decision execution module 16 in the heat dissipation performance optimization system of the multi-layer structure cable duct is further used to: A collaborative decision trigger analysis is performed based on the sliding window heat dissipation decision; if the collaborative decision trigger analysis result is a trigger result, the hot zone distribution is sent to the collaborative sensor, and a collaborative request is reported, and a collaborative control decision is generated according to the collaborative request and the hot zone distribution, and the collaborative control decision is used to perform heat dissipation management of multi-layer structure cable troughs.

[0093] Furthermore, the decision execution module 16 in the heat dissipation performance optimization system of the multi-layer structure cable duct is further used to: If the temperature rise trend of any thermal management sub-zone meets the preset conditions in the sliding window, the thermal accumulation delay judgment of the adjacent sub-zone of the corresponding thermal management sub-zone is executed; if the thermal accumulation delay judgment of the adjacent sub-zone is passed, the collaborative decision trigger analysis result is used as the trigger result, and a temperature trend linkage instruction is established; after the thermal zone distribution is selected using the temperature trend linkage instruction, it is synchronized to the collaborative sensor; the collaborative sensor is used to make a thermal trend linkage decision for the associated sub-zone to generate a collaborative control decision.

[0094] Furthermore, the heat dissipation performance optimization system of the multi-layer structure cable trunking further includes an aggregation optimization module, which is further used to: The instantaneous start-up identification of the cable load is performed on the thermal management sub-area, and the heat cluster aggregation judgment is performed according to the number of instantaneous starts; if the heat cluster aggregation judgment is passed, the collaborative decision trigger analysis result is the trigger result; after the heat cluster aggregation distribution is established, the collaborative sensor is used to perform multi-objective collaborative optimization and establish a collaborative control decision. The multi-objective collaborative optimization includes spatial heat redistribution optimization, duct load linkage adjustment optimization, thermal capacity enhancement of adjacent thermal management sub-areas, and scheduling coordination optimization.

[0095] Furthermore, the heat dissipation performance optimization system of the multi-layer structure cable trunking further includes a heat dissipation failure module, which is further used to: Control positioning is performed on all thermal management sub-areas under the activation of maximum heat dissipation power; the temperature control effect is verified using the control positioning results. If the temperature control effect verification result is a non-cooling result, the collaborative decision trigger analysis result is the trigger result; the shared heat dissipation requirements of adjacent sub-areas are established, and the shared heat dissipation requirements are used to generate collaborative control decisions.

[0096] Furthermore, the heat dissipation performance optimization system of the multi-layer structure cable trunking further includes an air duct conflict module, and the air duct conflict module is further used to: Determine whether there is a shared air duct between the cooling thermal management sub-zone and the high-temperature thermal management sub-zone; if so, the collaborative decision trigger analysis result is the trigger result, and the cooling path transfer requirement of the high-temperature thermal management sub-zone is established, and the cooling path transfer requirement is used to generate a collaborative control decision.

[0097] Furthermore, the heat dissipation performance optimization system of the multi-layer structure cable trunking further includes an abnormality identification module, which is further used to: Activate the abnormality recognition layer, receive the real-time monitoring data of the sensor array with the abnormality recognition layer, and perform global abnormality analysis; use the thermal runaway trend trigger result of the global abnormality analysis to report the heat dissipation abnormality.

[0098] Furthermore, the heat dissipation performance optimization system of the multi-layer structure trunking further includes a high temperature emergency module, which is further used to: The thermal runaway trend is used to establish a high-temperature fault location; based on the high-temperature fault location, an emergency heat dissipation mechanism is activated to perform emergency management.

[0099] Furthermore, the heat dissipation performance optimization system of the multi-layer structure trunking further includes a heat dissipation evaluation module, which is further used to: Establish a heat dissipation evaluation for each thermal management sub-area; use the heat dissipation evaluation to perform adaptive reinforcement learning on the calibration decision maker after incremental optimization, and use the calibration decision maker after adaptive reinforcement learning to perform heat dissipation management on the corresponding thermal management sub-area.

[0100] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The heat dissipation performance optimization method and specific examples of the multi-layer structure cable trough in Example 1 are also applicable to the heat dissipation performance optimization system of the multi-layer structure cable trough in this embodiment. Through the above detailed description of the heat dissipation performance optimization method of the multi-layer structure cable trough, those skilled in the art can clearly understand the heat dissipation performance optimization system of the multi-layer structure cable trough in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0101] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0102] Obviously, for those skilled in the art, several improvements and modifications can be made to the present application without departing from the principles of the present application, and these improvements and modifications also fall within the scope of protection of the present application.

Claims

1. A method for optimizing the heat dissipation performance of a multi-layer structure cable duct, characterized in that: include: Perform cable heating fitting analysis on the cables and use the cable heating fitting analysis results to divide the multi-layer cable duct into multiple thermal management sub-areas; A sensor array is configured for each thermal management sub-area, and a thermal zone distribution is established using the sensor array; Performing working fitting on the multi-layer structure cable duct, establishing a heat partition fitting result, and establishing a calibration decision maker using the heat partition fitting result; After distributing the calibration decision maker to a plurality of thermal management sub-areas, performing incremental optimization of the calibration decision maker; The incrementally optimized calibration decision maker is used to make sliding window cooling decisions based on the corresponding hot zone distribution. Using sliding window heat dissipation decision to manage heat dissipation of cables in multi-layer structure cable ducts.

2. The method for optimizing the heat dissipation performance of a multi-layer structure cable trunking according to claim 1, wherein: The method of utilizing sliding window heat dissipation decision to perform heat dissipation management of cables in multi-layer structure cable ducts includes: Performing collaborative decision triggering analysis based on the sliding window heat dissipation decision; If the collaborative decision trigger analysis result is a trigger result, the hot zone distribution is sent to the collaborative sensor and a collaborative request is reported. A collaborative control decision is generated based on the collaborative request and the hot zone distribution, and the collaborative control decision is used to perform heat dissipation management of multi-layer structure cable troughs.

3. The method for optimizing the heat dissipation performance of a multi-layer structure cable trunking according to claim 2, wherein: If the collaborative decision trigger analysis result is a trigger result, the hot zone distribution is sent to the collaborative sensor and a collaborative request is reported, including: If the temperature rise trend of any thermal management sub-area meets the preset conditions in the sliding window, the thermal accumulation delay judgment of the adjacent sub-area of ​​the corresponding thermal management sub-area is performed; If the adjacent sub-area heat accumulation delay judgment passes, the collaborative decision trigger analysis result is the trigger result, and the temperature trend linkage instruction is established; After selecting the heat zone distribution using the temperature trend linkage instruction, the distribution is synchronized to the collaborative sensor; The collaborative sensor is used to make a thermal trend linkage decision for the associated sub-areas and generate a collaborative control decision.

4. The method for optimizing the heat dissipation performance of a multi-layer structure cable trunking according to claim 2, wherein: If the collaborative decision trigger analysis result is a trigger result, the hot zone distribution is sent to the collaborative sensor and a collaborative request is reported, further comprising: Identify the instantaneous start of cable loads in the thermal management sub-area and perform heat clustering determination based on the number of instantaneous starts; If the hot cluster aggregation is judged to be passed, the collaborative decision-making trigger analysis result is the trigger result; After establishing the distribution of heat clusters, the collaborative sensor is used to perform multi-objective collaborative optimization and establish collaborative control decisions. The multi-objective collaborative optimization includes spatial heat redistribution optimization, duct load linkage adjustment optimization, heat capacity enhancement of adjacent thermal management sub-areas, and scheduling coordination optimization.

5. The method for optimizing the heat dissipation performance of a multi-layer structure cable trunking according to claim 2, wherein: If the collaborative decision trigger analysis result is a trigger result, the hot zone distribution is sent to the collaborative sensor and a collaborative request is reported, further comprising: Control and position all thermal management sub-areas under maximum heat dissipation power activation; The temperature control effect is verified using the control positioning result. If the temperature control effect verification result is not a cooling result, the collaborative decision-making trigger analysis result is a trigger result; Shared heat dissipation requirements of adjacent sub-areas are established, and collaborative control decisions are generated using the shared heat dissipation requirements.

6. The method for optimizing the heat dissipation performance of a multi-layer structure cable trunking according to claim 2, wherein: If the collaborative decision trigger analysis result is a trigger result, the hot zone distribution is sent to the collaborative sensor and a collaborative request is reported, further comprising: Determine whether there is a shared air duct between the cooling thermal management sub-area and the high-temperature thermal management sub-area; If so, the collaborative decision trigger analysis result is used as the trigger result, and the cooling path transfer requirement of the high-temperature thermal management sub-area is established, and the cooling path transfer requirement is used to generate a collaborative control decision.

7. The method for optimizing the heat dissipation performance of a multi-layer structure cable trunking according to claim 1, wherein: The method of using the sliding window heat dissipation decision to perform heat dissipation management of cables in multi-layer cable ducts includes: activating an anomaly recognition layer to receive real-time monitoring data from the sensor array and perform global anomaly analysis; The thermal runaway trend trigger result of the global abnormality analysis is used to report the heat dissipation abnormality.

8. The method for optimizing the heat dissipation performance of a multi-layer structure cable trunking according to claim 7, wherein: The method of using the thermal runaway trend trigger result of the global abnormality analysis to report a heat dissipation abnormality includes: Establishing high temperature fault location using the thermal runaway trend; Based on the high temperature fault location, an emergency heat dissipation mechanism is activated to perform emergency management.

9. The method for optimizing the heat dissipation performance of a multi-layer structure cable trunking according to claim 1, wherein: After the sliding window heat dissipation decision is used to perform heat dissipation management of cables in multi-layer structure cable troughs, the method further includes: Establish heat dissipation evaluation for each thermal management sub-area; The calibration decision maker after incremental optimization is adaptively enhanced by using the heat dissipation evaluation, and the calibration decision maker after adaptive reinforcement learning is used to perform heat dissipation management of the corresponding heat management sub-area.

10. The heat dissipation performance optimization system of the multi-layer structure trunking is characterized by: The steps for implementing the method for optimizing the heat dissipation performance of a multi-layer structure cable trough according to any one of claims 1 to 9, wherein the heat dissipation performance optimization system of the multi-layer structure cable trough comprises: The sub-area division module is used to perform cable heating fitting analysis on the cable and divide the multi-layer structure cable trunking into multiple thermal management sub-areas using the cable heating fitting analysis results; A sensor configuration module is used to configure a sensor array for each thermal management sub-area and establish a thermal zone distribution using the sensor array; A heating zone fitting module is used to perform working fitting on multi-layer structure cable ducts, establish heating zone fitting results, and establish a calibration decision maker using the heating zone fitting results; A decision maker optimization module, configured to distribute the calibration decision maker to a plurality of thermal management sub-areas and then perform incremental optimization of the calibration decision maker; A decision determination module, configured to use the incrementally optimized calibrated decision maker to make sliding window heat dissipation decisions based on the corresponding hot zone distribution; The decision execution module is used to manage the heat dissipation of cables in multi-layer structure cable ducts by using sliding window heat dissipation decisions.

Images